Boese0601/MagicDance
[ICML 2024] MagicPose(also known as MagicDance): Realistic Human Poses and Facial Expressions Retargeting with Identity-aware Diffusion
This project helps creators and animators generate realistic videos of people moving and expressing emotions. You provide a reference image of a person and a sequence of desired poses and facial expressions (like from a dance video), and the system generates a new video of that person performing the exact movements and expressions while maintaining their identity. It's ideal for anyone creating digital characters or realistic human animations.
777 stars. No commits in the last 6 months.
Use this if you need to transfer complex human poses and detailed facial expressions from one video or sequence to a specific character's image, producing a highly realistic and identity-aware animation.
Not ideal if you need to generate entirely new characters or environments, as this tool focuses specifically on retargeting human motion and expressions onto an existing person's likeness.
Stars
777
Forks
65
Language
Python
License
—
Category
Last pushed
Jul 03, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/Boese0601/MagicDance"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
PRIS-CV/DemoFusion
Let us democratise high-resolution generation! (CVPR 2024)
mit-han-lab/distrifuser
[CVPR 2024 Highlight] DistriFusion: Distributed Parallel Inference for High-Resolution Diffusion Models
Tencent-Hunyuan/HunyuanPortrait
[CVPR-2025] The official code of HunyuanPortrait: Implicit Condition Control for Enhanced...
giuvecchio/matfuse
MatFuse: Controllable Material Generation with Diffusion Models (CVPR2024)
Shilin-LU/TF-ICON
[ICCV 2023] "TF-ICON: Diffusion-Based Training-Free Cross-Domain Image Composition" (Official...